docs: Unsloth-style KerasFormers model card for detr-resnet-101
Browse files
README.md
CHANGED
|
@@ -26,8 +26,6 @@ Paper: [End-to-End Object Detection with Transformers (arXiv:2005.12872)](https:
|
|
| 26 |
|
| 27 |
DETR (DEtection TRansformer) treats object detection as direct set prediction. A ResNet backbone produces a feature map, a transformer encoder-decoder attends over it with a fixed set of learned object queries, and each query emits one class and one box. Training uses a bipartite (Hungarian) matching loss, so every ground-truth object is assigned exactly one query. That framing removes anchors and NMS. Panoptic checkpoints add a mask head for things and stuff.
|
| 28 |
|
| 29 |
-
Architecture (this port): ResNet backbone, transformer encoder-decoder with learned object queries (`num_queries=100`), class/box heads, and (for panoptic) a mask head. Hungarian matching at train time; inference keeps high-scoring queries after dropping the no-object class.
|
| 30 |
-
|
| 31 |
For more details on the model, please go to Facebook's original [model card](https://huggingface.co/facebook/detr-resnet-101).
|
| 32 |
|
| 33 |
Pure-**Keras 3** conversion of [`facebook/detr-resnet-101`](https://huggingface.co/facebook/detr-resnet-101) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
|
|
|
|
| 26 |
|
| 27 |
DETR (DEtection TRansformer) treats object detection as direct set prediction. A ResNet backbone produces a feature map, a transformer encoder-decoder attends over it with a fixed set of learned object queries, and each query emits one class and one box. Training uses a bipartite (Hungarian) matching loss, so every ground-truth object is assigned exactly one query. That framing removes anchors and NMS. Panoptic checkpoints add a mask head for things and stuff.
|
| 28 |
|
|
|
|
|
|
|
| 29 |
For more details on the model, please go to Facebook's original [model card](https://huggingface.co/facebook/detr-resnet-101).
|
| 30 |
|
| 31 |
Pure-**Keras 3** conversion of [`facebook/detr-resnet-101`](https://huggingface.co/facebook/detr-resnet-101) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
|